Unverified50% confidenceBenchmarkExact time
Opus 5.5 scored 67 on Humanity's Last Exam, Astra scored 57, and Fable 5.1 scored 65.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/25/2026
First Seen
Valid until: 12/24/2026
Sources
Related Entities
Related Claims
UnverifiedClaude 5.1 scored 60.9% on Humanities Last Exam without tools, rising to 65% with tools enabled.71% similarUnverifiedGPT-5.6 Sol achieved the highest score on Humanity's Last Exam at a price far below that of Claude Opus and Fable.68% similarUnverifiedOn Terminal Bench 4.0, Opus 5.5 scored 66.4%, Astra scored 57.9%, Fable 5.1 scored 55.8%, and the previous generation Opus 5 scored 52.3%.67% similarUnverifiedClaude Opus 4.7 at an intermediate checkpoint achieves a pass rate of 57%, yet its final accuracy is only 39.8%66% similarUnverifiedGPT-5.6 set a new all-time high score of 53.6 on the Agent's Last Exam benchmark, surpassing Claude Opus 4.5 by 13.1 points.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949380API
curl https://kongchang.com/api/v1/knowledge/claims/949380MCP
get_claim(id=949380)